{"id":"https://openalex.org/W1420406291","doi":"https://doi.org/10.1007/978-3-642-25944-9_24","title":"Actor-Critic Algorithm Based on Incremental Least-Squares Temporal Difference with Eligibility Trace","display_name":"Actor-Critic Algorithm Based on Incremental Least-Squares Temporal Difference with Eligibility Trace","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1420406291","doi":"https://doi.org/10.1007/978-3-642-25944-9_24","mag":"1420406291"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-25944-9_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-25944-9_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, P.R. China","School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, P.R. China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, P.R. China#TAB#","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035404403","display_name":"Huan-Ting FENG","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanting Feng","raw_affiliation_strings":["School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, P.R. China","School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, P.R. China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, P.R. China#TAB#","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, P.R. China","School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221116, P.R. China","institution_ids":["https://openalex.org/I25757504"]},{"raw_affiliation_string":"School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, P.R. China#TAB#","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091364297"],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13740359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.946399986743927,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13832","display_name":"Advanced Decision-Making Techniques","score":0.9354000091552734,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.8824136853218079},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8755321502685547},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.7395545244216919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713250994682312},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7057103514671326},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6071739792823792},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5486557483673096},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5277826189994812},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4960416257381439},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4884738028049469},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.45475897192955017},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.43806105852127075},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40431174635887146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2761627435684204},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21090927720069885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2040610909461975},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16198131442070007}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.8824136853218079},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8755321502685547},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.7395545244216919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713250994682312},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7057103514671326},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6071739792823792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5486557483673096},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5277826189994812},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4960416257381439},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4884738028049469},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.45475897192955017},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.43806105852127075},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40431174635887146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2761627435684204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21090927720069885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2040610909461975},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16198131442070007},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-642-25944-9_24","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-25944-9_24","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W2072931156","https://openalex.org/W2094387729","https://openalex.org/W2100677568","https://openalex.org/W2121863487","https://openalex.org/W2126410641","https://openalex.org/W2132351269","https://openalex.org/W2136602922","https://openalex.org/W2155027007","https://openalex.org/W2172968643","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4308702637","https://openalex.org/W2149418961","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W3038962357","https://openalex.org/W61119710","https://openalex.org/W2971484784","https://openalex.org/W4288112126","https://openalex.org/W2011233848","https://openalex.org/W2808418668"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
